태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Models that learn to segment each image (i.e. assign a class to every pixel) without seeing the ground truth labels.
<span style="color:grey; opacity: 0.6">( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )</span>
관련 논문에서 소개한 기법입니다. 이 태스크에서의 평가 여부는 평가 결과에서 확인하세요.
DeepCluster is a self-supervision approach for learning image representations. DeepCluster iteratively groups the features with a standard clustering algorithm, k-means, and uses the subsequent assignments as supervision to update the weights of the network
Deep Clustering for Unsupervised Learning of Visual Features
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.